DiffListener: Discrete Diffusion Model for Listener Generation
- URL: http://arxiv.org/abs/2502.06822v1
- Date: Wed, 05 Feb 2025 07:57:15 GMT
- Title: DiffListener: Discrete Diffusion Model for Listener Generation
- Authors: Siyeol Jung, Taehwan Kim,
- Abstract summary: The listener head generation task aims to generate natural nonverbal listener responses based on the speaker's multimodal cues.
We propose DiffListener, a discrete diffusion based approach for non-autoregressive listener head generation.
Our model takes the speaker's facial information, audio, and text as inputs, additionally incorporating facial differential information to represent the temporal dynamics of expressions and movements.
- Score: 2.80888070977859
- License:
- Abstract: The listener head generation (LHG) task aims to generate natural nonverbal listener responses based on the speaker's multimodal cues. While prior work either rely on limited modalities (e.g. audio and facial information) or employ autoregressive approaches which have limitations such as accumulating prediction errors. To address these limitations, we propose DiffListener, a discrete diffusion based approach for non-autoregressive listener head generation. Our model takes the speaker's facial information, audio, and text as inputs, additionally incorporating facial differential information to represent the temporal dynamics of expressions and movements. With this explicit modeling of facial dynamics, DiffListener can generate coherent reaction sequences in a non-autoregressive manner. Through comprehensive experiments, DiffListener demonstrates state-of-the-art performance in both quantitative and qualitative evaluations. The user study shows that DiffListener generates natural context-aware listener reactions that are well synchronized with the speaker. The code and demo videos are available in https://siyeoljung.github.io/DiffListener
Related papers
- DiffTED: One-shot Audio-driven TED Talk Video Generation with Diffusion-based Co-speech Gestures [27.763304632981882]
We introduce DiffTED, a new approach for one-shot audio-driven talking video generation from a single image.
We leverage a diffusion model to generate sequences of keypoints for a Thin-Plate Spline motion model.
Experiments demonstrate that DiffTED generates temporally coherent talking videos with diverse co-speech gestures.
arXiv Detail & Related papers (2024-09-11T22:31:55Z) - Emotional Listener Portrait: Realistic Listener Motion Simulation in
Conversation [50.35367785674921]
Listener head generation centers on generating non-verbal behaviors of a listener in reference to the information delivered by a speaker.
A significant challenge when generating such responses is the non-deterministic nature of fine-grained facial expressions during a conversation.
We propose the Emotional Listener Portrait (ELP), which treats each fine-grained facial motion as a composition of several discrete motion-codewords.
Our ELP model can not only automatically generate natural and diverse responses toward a given speaker via sampling from the learned distribution but also generate controllable responses with a predetermined attitude.
arXiv Detail & Related papers (2023-09-29T18:18:32Z) - MFR-Net: Multi-faceted Responsive Listening Head Generation via
Denoising Diffusion Model [14.220727407255966]
Responsive listening head generation is an important task that aims to model face-to-face communication scenarios.
We propose the textbfMulti-textbfFaceted textbfResponsive Listening Head Generation Network (MFR-Net)
arXiv Detail & Related papers (2023-08-31T11:10:28Z) - Can Language Models Learn to Listen? [96.01685069483025]
We present a framework for generating appropriate facial responses from a listener in dyadic social interactions based on the speaker's words.
Our approach autoregressively predicts a response of a listener: a sequence of listener facial gestures, quantized using a VQ-VAE.
We show that our generated listener motion is fluent and reflective of language semantics through quantitative metrics and a qualitative user study.
arXiv Detail & Related papers (2023-08-21T17:59:02Z) - DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven
Portraits Animation [78.08004432704826]
We model the Talking head generation as an audio-driven temporally coherent denoising process (DiffTalk)
In this paper, we investigate the control mechanism of the talking face, and incorporate reference face images and landmarks as conditions for personality-aware generalized synthesis.
Our DiffTalk can be gracefully tailored for higher-resolution synthesis with negligible extra computational cost.
arXiv Detail & Related papers (2023-01-10T05:11:25Z) - Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion [89.01668641930206]
We present a framework for modeling interactional communication in dyadic conversations.
We autoregressively output multiple possibilities of corresponding listener motion.
Our method organically captures the multimodal and non-deterministic nature of nonverbal dyadic interactions.
arXiv Detail & Related papers (2022-04-18T17:58:04Z) - DFA-NeRF: Personalized Talking Head Generation via Disentangled Face
Attributes Neural Rendering [69.9557427451339]
We propose a framework based on neural radiance field to pursue high-fidelity talking head generation.
Specifically, neural radiance field takes lip movements features and personalized attributes as two disentangled conditions.
We show that our method achieves significantly better results than state-of-the-art methods.
arXiv Detail & Related papers (2022-01-03T18:23:38Z) - Responsive Listening Head Generation: A Benchmark Dataset and Baseline [58.168958284290156]
We define the responsive listening head generation task as the synthesis of a non-verbal head with motions and expressions reacting to the multiple inputs.
Unlike speech-driven gesture or talking head generation, we introduce more modals in this task, hoping to benefit several research fields.
arXiv Detail & Related papers (2021-12-27T07:18:50Z) - Deep Variational Generative Models for Audio-visual Speech Separation [33.227204390773316]
We propose an unsupervised technique based on audio-visual generative modeling of clean speech.
To better utilize the visual information, the posteriors of the latent variables are inferred from mixed speech.
Our experiments show that the proposed unsupervised VAE-based method yields better separation performance than NMF-based approaches.
arXiv Detail & Related papers (2020-08-17T10:12:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.